Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Ab Test Engine

ASecurity

Use for A/B experiments on OpenAmer configs and skills.

5 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentspythonbash

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add openamer/openamer --skill ab-test-engine --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ab Test Engine?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Ab Test Engine
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/openamer-ab-test-engine/badge)](https://www.skillsdirectory.com/skills/openamer-ab-test-engine)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: ab-test-engine
description: Use for A/B experiments on OpenAmer configs and skills.
---

# A/B Test Engine

CLI-Tool für automatische Experimente mit Skills + Configs in OpenAmer.

## Verzeichnisse

| Pfad | Zweck |
|------|-------|
| `~/.ab-tests/experiments/` | JSON-Experimentdefinitionen |
| `~/.ab-tests/results/` | Ergebnisdaten pro Experiment |
| `~/.ab-tests/metrics/` | Raw-Metrik-Snapshots |

## CLI-Befehle

```bash
python scripts/ab-test-engine.py --create <name> '<beschreibung>' --variant 'key=value[,key=value]'
python scripts/ab-test-engine.py --list
python scripts/ab-test-engine.py --status <name>
python scripts/ab-test-engine.py --conclude <name>
python scripts/ab-test-engine.py --collect
python scripts/ab-test-engine.py --analyze
python scripts/ab-test-engine.py --switch <name> --to variant|control
python scripts/ab-test-engine.py --restore <name>
```

## Workflow

### 1. Experiment anlegen
```bash
python scripts/ab-test-engine.py --create skill-loader-test "Vergleicht lazy vs eager Skill-Loader" --variant 'skill_loader=lazy,skill_cache_size=512'
```

### 2. Automatische Metrikerfassung
- `--collect` → alle 30 min (Cron-Job)
- Liest Cron-Exit-Codes, Dauer, RAM-Nutzung
- Bildet Composite Score aus Exit-Codes (60%), Dauer (30%), RAM (10%)

### 3. Statistische Analyse
```bash
python scripts/ab-test-engine.py --conclude skill-loader-test
```
- Welch's t-Test (ungleiche Varianzen)
- p-Wert + Cohen's d
- Winner-Empfehlung

### 4. Automation (Cron)

Im OpenAmer-Cron einrichten:

```yaml
- name: ab-test-collect
  schedule: "*/30 * * * *"
  command: python scripts/ab-test-engine.py --collect
  description: Sammelt A/B-Test-Metriken alle 30min

- name: ab-test-analyze
  schedule: "0 6 * * *"
  command: python scripts/ab-test-engine.py --analyze
  description: Analysiert abgelaufene A/B-Tests täglich 6 Uhr
```

## Fallstricke

- **Mindestens 3 Samples pro Gruppe** nötig für t-Test
- Bei < 2 Samples wird σ=0 gesetzt
- RAM-Messung ohne `psutil` ist ungenau (Fallback WMIC / fixed total)
- `--switch` verändert die aktive `config.yaml` direkt
- Cron-Log-Pfad: `$OPENAMER_HOME/cron/cron.log`
- Normalapproximation bei df > 100 für p-Wert
- Nutze `--restore` um Config auf Control-Zustand zurückzusetzen

Attribution

openameropenamer
View sourceSee grades on GitHubMore from openamer →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →